Study on the Safety and Prevention Technology of Coal Mining under the River in Xingyuan Coal Mine

Coal mining-induced surface subsidence poses significant ecological and infrastructural challenges, necessitating a comprehensive study to ensure safe mining practices, particularly in underwater conditions. This project aims to address the extensive impact of coal mining on the environment, infrastructure, and overall safety, focusing on the Shigong River area above the working face. The study employs qualitative and quantitative analyses, along with on-site engineering measurements, to gather data on crucial parameters such as coal seam characteristics, roof rock lithology, thickness, water resistance, and structural damage degree. The research encompasses a multidisciplinary approach, involving mining, geology, hydrogeology, geophysical exploration, rock mechanics, mine surveying, and computational mathematics. The importance of effective safety measures and prevention techniques is emphasized, laying the foundation for research focused on the Xingyun coal mine. The brief concludes by highlighting the potential economic and social benefits of this project and its contribution to valuable experience for future subsea coal mining.

Research on the Application of Virtual Simulation Technology in the Safety Management of Coal Mining

Safety is paramount in coal mining as it affects efficiency.Thus,it is essential to enhance the management of coal mine safety.With the ongoing advancement of modern technologies,more innovative solutions are being integrated into the safety management of coal mining,including virtual simulation technology.This paper focuses on analyzing and researching the application of virtual simulation technology in the safety management of coal mining,providing insights for reference.

Smart industrial IoT empowered crowd sensing for safety monitoring in coal mine

The crowd sensing technology can realize the sensing and computing of people,machines,and environment in smart industrial IoT-based coal mine,which provides a solution for safety monitoring through distributed intelligence optimization.However,due to the difficulty of neural network training to achieve global optimality and the fact that traditional LSTM methods do not consider the relationship between adjacent machines,the accuracy of human body position prediction and pressure value prediction is not high.To solve these problems,this paper proposes a smart industrial IoT empowered crowd sensing for safety monitoring in coal mine.First,we propose a Particle Swarm Optimization-Elman Neural Network(PE)algorithm for the mobile human position prediction.Second,we propose an ADI-LSTM neural network prediction algorithm for pressure values of machines supports in underground mines.Among them,our proposed PE algorithm has the lowest average cumulative prediction error,and the trajectory fit rate is improved by 24.1%,13.9%and 8.7%compared with Kalman filtering,Elman and Kalman plus Elman algorithms,respectively.Meanwhile,compared with single-input ARIMA,RNN,LSTM,and GRU,the RMSE values of our proposed ADI-LSTM are reduced by 36.6%,52%,32%,and 13.7%,respectively;and the MAPE values are reduced by 0.0003%,0.9482%,1.1844%,and 0.3620%,respectively.

基于差分非平稳Transformer的液压支架立柱压力预测

液压支架立柱压力预测是回采工艺决策的重要依据,也是确保围岩稳定的基础信息之一。然而,液压支架立柱压力虽然具有一定的规律性,却无法用简单的数学模型进行预测;且在回采过程中,支架不接顶、顶板破碎、传感器检测误差等带来大量的随机噪声,使得压力数据劣化为非平稳时间序列,给压力的预测带来的很大的困难。本文在Transformer基础上,提出一种差分非平稳Transformer模型,在Transformer的编码器和解码器中分别引入差分归一化和反归一化操作,以提升序列的平稳性。同时,在Transformer中采用去平稳注意力机制,计算序列元素之间的关联关系,以增强模型的预测能力。在真实的煤矿支架立柱数据集上的对比实验表明,本文提出的差分非平稳Transformer的预测效果达到0.674,表现明显优于LSTM、Transformer和非平稳Transformer模型。

宽负荷下切圆燃煤锅炉H_(2)S分布特性的数值模拟

锅炉采用空气分级燃烧降低NO_(x)排放的同时也提高了主燃区H_(2)S体积分数。炉墙壁面过高的H_(2)S体积分数是加剧水冷壁高温腐蚀的重要因素。为保障新能源并网发电,大型燃煤机组灵活调峰的需求增加,不同负荷下的水冷壁近壁面H_(2)S分布特性值得关注。通过正交试验分析了切圆燃煤锅炉运行参数对水冷壁近壁面H_(2)S体积分数分布的影响。选取一台超临界600 MW切圆燃煤锅炉建立数值模型,设计L_(16)(4^(5))正交工况,覆盖100%BMCR、75%THA,50%THA以及35%BMCR四种负荷。建立了自定义SO_(x)生成模型以确定燃料硫的析出和转化路径,模型包含多表面反应子模型以描述焦炭与O_(2)/CO_(2)/H_(2)O等3种气体的异相反应,并确定焦炭气化反应消耗量占总消耗量的比例,进而对炉膛H_(2)S空间分布进行了模拟计算。研究表明,近壁面高体积分数H_(2)S区域主要位于投运燃烧器层中最下层燃烧器以下以及最上层燃烧器以上至SOFA层之间,烟气切圆沿炉膛高度增加逐渐增大是造成后一区域H_(2)S体积分数较高的重要原因。35%BMCR负荷下水冷壁重点区域的H_(2)S平均体积分数为364μL/L,明显低于其他负荷。锅炉运行参数对重点区域H_(2)S体积分数影响程度的排序为:锅炉负荷>一次风率>主燃区空气过量系数>假想切圆直径>燃烧器竖直摆角。

基于SEM的煤矿工人易发不安全行为控制研究

为了准确识别煤矿工人易发不安全行为,预防由此导致的煤矿事故,文章首先构建了由作业过程、工艺设备、环境限制和作业决策4个一级指标和操作错误等18个二级指标构成的煤矿工人不安全行为评价指标体系。其次,将结构方程模型(SEM)运用到了煤矿工人易发不安全行为控制研究中。研究结果表明:作业过程等4个一级指标(潜在变量)均对煤矿工人不安全行为的发生具有显著影响;18个二级指标(观测变量)中,有无视警示进入危险区域等14种煤矿工人易发不安全行为,且根据路径系数得到了其易发程度。最后,提出了控制煤矿工人易发不安全行为的对策。文章为煤矿工人不安全行为研究提供了一种方法。

基于改进YOLOX-S的轻量化煤矸石检测方法研究

目的 为了探索基于现有机器视觉煤矸石检测方法的模型参数量、计算量对检测速度和嵌入式设备的影响,方法 提出一种基于改进的无锚框YOLOX-S轻量化煤矸石检测模型。为使模型能提取更真实的煤矸石特征信息,收集分选现场煤矸石样本,保证实际环境下的煤矸石检测效果,适应实际生产环境。结合CSPNet,将输入的特征图分割成两个分支,实现更丰富的梯度组合,同时减少模型计算量;之后在其中一条分支使用Ghost轻量化卷积,通过少量常规卷积生成一组特征图,达到初次减少计算量和参数量的效果,然后在此特征图基础上经过简单线性变化操作,生成一组新的特征图,将两组特征图进行融合,降低对计算资源需求的同时,也达到了常规卷积相同的特征提取效果;引入LeakyReLU激活函数减弱模型梯度消失的影响,提取更深更多的特征信息;最后融合两个分支特征,保证较高的检测精度,提升模型检测速度。采用CIOU Loss(complete IOU loss)优化目标边界框回归损失函数,使模型回归损失收敛更快,提高模型目标定位能力。结果 与原模型相比,本文改进模型在保证较高的平均精度均值90.51%情况下,模型参数减少47%,计算量减少49%,检测速度达到50帧/s。结论 轻量化煤矸石检测模型使智能化煤矸石检测在实际生产环境中具有一定的应用前景。

煤层H_(2)S与煤脱硫协同治理研究

为研究煤层H_(2)S与煤脱硫的协同治理,自制装置对复配碱液进行H_(2)S吸收和煤脱硫试验。采用离子色谱法、X射线光电子能谱、形态硫测试对吸收液和煤样进行表征,分析协同治理机理,利用响应面法分析各因素对H_(2)S吸收和煤脱硫的影响程度。结果显示:单一碱液均可吸收H_(2)S,但脱硫效果微弱;添加NaClO后,协同治理效果显著且能避免H_(2)S二次逸散,其中NaOH+NaClO协同治理效果最优。在反应后,H_(2)S及煤中低价态硫噻吩、硫醇和硫醚减少,吸收液中SO_(4)^(2-)及煤中高价态硫(亚)砜增加,表明NaOH为元素硫歧化提供碱性条件,元素硫继而被NaClO氧化。NaOH质量浓度对H_(2)S吸收影响最大,NaClO质量浓度对煤脱硫影响最大,NaOH和NaClO交互对煤脱硫与H_(2)S吸收影响显著。利用Design-Expert软件确定最佳参数:NaOH质量浓度为54 g/L、NaClO质量浓度为54 g/L、温度为21.4℃。

基于改进YOLO v7和DeepSORT的罐笼人员跟踪计数方法

煤矿副井罐笼载人时,超载现象时有发生,给副井运输安全带来了隐患。针对该问题,提出了基于改进YOLO v7和DeepSORT的罐笼人员跟踪计数方法。首先利用煤矿副井罐笼区域的监控摄像头采集的视频制作罐笼行人数据集,再利用改进的YOLO v7对罐笼人员进行识别:基于GhostNet网络改进YOLO v7以提升模型的实时性;通过引入ACmix注意力机制提升模型对副井复杂背景人员的感知能力,并基于SIoU损失函数进一步增强模型的鲁棒性;最后利用优化后的DeepSORT算法对罐笼人员进行跟踪计数:基于CIOU优化DeepSORT算法的匹配准确度,使目标追踪更加稳定。试验结果表明:在构建的CP dataset数据集上,改进后的YOLO v7网络的均值平均精度mAP达到了97.4%,算法的跟踪准确性MOTA和跟踪精度MOTP分别达到了95.74%和94.26%。

Mechanism of micro-wetting of highly hydrophobic coal dust in underground mining and new wetting agent development

The internal mechanism of the high hydrophobicity of the coal samples from the Pingdingshan mining area was studied through industrial,element,and surface functional group analysis.Laboratory testing and molecular dynamics simulations were employed to study the impact of three types of surfactants on the surface adsorption properties and wettability of highly hydrophobic bituminous coal.The results show that the surface of highly hydrophobic bituminous coal is compact,rich in inorganic minerals,and poorly wettable and that coal molecules are dominated by hydrophobic functional groups of aromatic rings and aliphatic structures.The wetting performance of surfactants as the intermediate carrier to connect coal and water molecules is largely determined by the interaction force between surfactants and coal(Fs-c)and the interaction force between surfactants and water(Fs-w),which effectively improve the wettability of modified coal dust via modifying its surface electrical properties and surface energy.A new type of wetting agent with a dust removal rate of 89%has been developed through discovery of a compound wetting agent solution with optimal wetting and settling performance.This paper provides theoretical and technical support for removing highly hydrophobic bituminous coal dust in underground mining.

Characteristics of coal resources in China and statistical analysis and preventive measures for coal mine accidents

In the process of green and smart mine construction under the context of carbon neutrality,China's coal safety situation has been continuously improved in recent years.In order to recognize the development of coal production in China and prepare for future monitoring and prevention of safety incidents,this study mainly elaborated on the basic situation of coal resources and national mining accidents over the past five years(2017-2021),from four dimensions(accident level,type,region,and time),and then proposed the preventive measures based on accident statistical laws.The results show that the storage of coal resources has obvious geographic characteristics,mainly concentrated in the Midwest,with coal resources in Shanxi and Shaanxi accounting for about 49.4%.The proportion of coal consumption has dropped from 70.2%to 56%between 2011 and 2021,but still accounts for more than half of the all.Meanwhile,the accident-prone areas are positively correlated with the amount of coal production.Among different levels of coal mine accidents,general accidents had the highest number of accidents and deaths,with 692 accidents and 783 deaths,accounting for 87.6%and 54.64%respectively.The frequency of roof,gas,and transportation accidents is relatively high,and the number of single fatalities caused by gas accidents is the largest,about 4.18.In terms of geographical distribution of accidents,the safety situation in Shanxi Province is the most severe.From the time distribution of coal mine accidents,the accidents mainly occurred in July and August,and rarely occurred in February and December.Finally,the"4+4"safety management model is proposed,combining the statistical results with coal production in China.Based on the existing health and safety management systems,the manage-ments are divided into four sub-categories,and more specific measures are suggested.

面向煤矿安全监测边缘计算的YOLOv5s剪枝方法

目前,边缘计算与机器视觉相结合具有较好的煤矿安全监测应用前景,但边缘端存储空间和计算资源有限,高精度的复杂视觉模型难以部署。针对上述问题,提出了一种面向煤矿安全监测边缘端的基于间接和直接重要性评价空间融合(IDESF)的YOLOv5s剪枝方法,实现对YOLOv5s网络的轻量化。首先对YOLOv5s网络中各模块的卷积层进行结构分析,确定自由剪枝层和条件剪枝层,为后续分配剪枝率及计算卷积核剪枝数奠定基础。其次,根据基于卷积核权重幅值和层相对计算复杂度的卷积核权重重要性得分为可剪枝层分配剪枝率,有效降低剪枝后网络的计算复杂度。然后,基于卷积核直接重要性评价准则,将卷积层的间接输出重要性以缩放因子的形式引入直接重要性空间中,更新卷积核位置分布,构建包含卷积核输出信息和幅值信息的融合重要性评价空间,提高卷积核重要性评价的全面性。最后,借鉴topk投票的思想对中值滤波筛选冗余卷积核的流程进行优化,并用有向图的邻接矩阵中节点的入度来量化卷积核的冗余程度,提高了冗余卷积核筛选过程的可解释性和通用性。实验结果表明:①从平衡模型精度和轻量化程度的角度出发,剪枝率为50%的YOLOV5s_IDESF是最优的轻量级YOLOv5s。在VOC数据集上,YOLOv5s_IDESF的mAP@.5和mAP@0.5∶0.95均达到最高,分别为0.72和0.44,参数量降至最低2.65×10^(6),计算量降低至1.16×10^(9),综合复杂度也降至最低,图像处理帧率达到31.15帧/s。②在煤矿数据集上,YOLOv5s_IDESF的mAP@.5和mAP@0.5∶0.95均达到最高,分别为0.94和0.52,参数量降至最低3.12×10^(6),计算量降低至1.24×10^(9),综合复杂度也降至最低,图像处理帧率达到31.55帧/s。

Study of a Comprehensive Assessment Method for Coal Mine Safety Based on a Hierarchical Grey Analysis

Coal mine safety is a complex system, which is controlled by a number of interrelated factors and is difficult to estimate. This paper proposes an index system of safety assessment based on correlated factors involved in coal mining and a comprehensive evaluation model that combines the advantages of the AHP and a grey clustering method to guarantee the accuracy and objectivity of weight coefficients. First, we confirmed the weight of every index using the AHP, then did a general safety assessment by means of a grey clustering method. This model analyses the status of mining safety both qualitatively and quantitatively. It keeps management and technical groups informed of the situation of the coal production line in real time, which aids in making correct decisions based on practical safety issues. A case study in the application of the model is presented. The results show that the method is applicable and realistic with regard to the core of a coal mine's safety management. Consequently, the safe production of a mine and the awareness of advanced safe production management is accelerated.

Micromorphology and safety properties of meager and meager-lean coal for blast furnace injection

Four types of meager and meager-lean coal and one type of high-quality anthracite were selected based on the safety requirements for blast furnace coal injection and domestic coal quality to conduct microstructure and component analyses.The analyses of the organic and inorganic macerals and the chemical compositions of the selected coal samples indicate that the four types of meager and meager-lean coal have low volatilization,low ash content,and low sulfur content;these qualities are suitable for blast furnace injection.Grindability test was conducted on the four types of meager and meager-lean coal and the anthracite mixed coal samples.Results indicate that the mixture of meager and meager-lean coal and anthracite is beneficial to improve the grindability of pulverized coal.The explosive tests reveal that the selected coal samples are non-explosive or weakly explosive.When the proportion of meager and meager-lean coal is less than 40wt%,the mixed coal powder would not explode during the blowing process.The minimum ignition temperature test determines that the minimum ignition temperatures of the four types of meager and meager-lean coal and anthracite are 326,313,310,315,and 393°C,respectively.This study provides a guiding research idea for the safety of meager and meager-lean coal used in blast furnace injection.

Application of extension neural network to safety status pattern recognition of coalmines

In order to accurately and quickly identify the safety status pattern of coalmines,a new safety status pattern recognition method based on the extension neural network (ENN) was proposed,and the design of structure of network,the rationale of recognition algorithm and the performance of proposed method were discussed in detail.The safety status pattern recognition problem of coalmines can be regard as a classification problem whose features are defined in a range,so using the ENN is most appropriate for this problem.The ENN-based recognition method can use a novel extension distance to measure the similarity between the object to be recognized and the class centers.To demonstrate the effectiveness of the proposed method,a real-world application on the geological safety status pattern recognition of coalmines was tested.Comparative experiments with existing method and other traditional ANN-based methods were conducted.The experimental results show that the proposed ENN-based recognition method can identify the safety status pattern of coalmines accurately with shorter learning time and simpler structure.The experimental results also confirm that the proposed method has a better performance in recognition accuracy,generalization ability and fault-tolerant ability,which are very useful in recognizing the safety status pattern in the process of coal production.

Efficiency assessment of coal mine safety input by data envelopment analysis

In recent years improper allocation of safety input has prevailed in coal mines in China, which resulted in the frequent accidents in coal mining operation. A comprehensive assessment of the input efficiency of coal mine safety should lead to improved efficiency in the use of funds and management resources. This helps government and enterprise managers better understand how safety inputs are used and to optimize allocation of resources. Study on coal mine＇s efficiency assessment of safety input was con- ducted in this paper. A C^2R model with non-Archimedean infinitesimal vector based on output is established after consideration of the input characteristics and the model properties. An assessment of an operating mine was done using a specific set of input and output criteria. It is found that the safety input was efficient in 2002 and 2005 and was weakly efficient in 2003. However, the efficiency was relatively low in both 2001 and 2004. The safety input resources can be optimized and adjusted by means of projection theory. Such analysis shows that, on average in 2001 and 2004, 45% of the expended funds could have been saved. Likewise, 10% of the safety management and technical staff could have been eliminated and working hours devoted to safety could have been reduced by 12%. These conditions could have Riven the same results.

Research on effectiveness of coal mine safety supervision system reform on three types of collieries in China

Coal mine safety supervision system plays an important role in the coal mine safety management in China.However,the current supervision system is established on the basis of learning the advanced experience from other developed countries.It needs to be further improved according to national conditions.Therefore,the effectiveness of coal mine safety supervision system reform on three types of collieries are assessed by using time series analysis method based on comparative analysis of the supervision system before and after the reform in this paper.The regression results show that the structural reform is not conductive to the improvement of coal mine safety situation in the short term,but conductive significantly in the long term.Specifically,the effects in township coal mines are more significant than stateowned key coal mines in the long run,but negative effects also exist in the short term.The negative effects in state-owned key coal mines are non-significant compared with township coal mines.Moreover,the regression results are analyzed from the aspects of the closure policy of illegal small township coal mines at the end of 1998 and shortage of the new supervision system.Finally,the suggestions on improving the new supervision system are put forward based on the above analysis.

Safety diagnosis on coal mine production system based on fuzzy logic inference

According to the randomness and uncertainty of information in the safety diagnosis of coal mine production system (CMPS), a novel safety diagnosis method was proposed by applying fuzzy logic inference method, which consists of safety diagnosis fuzzifier, defuzzifier, fuzzy rules base and inference engine. Through the safety diagnosis on coal mine roadway rail transportation system, the result shows that the unsafe probability is about 0.5 influenced by no speed reduction and over quick turnout on roadway, which is the most possible reason leading to the accident of roadway rail transportation system.

Coal mine safety production forewarning based on improved BP neural network

Firstly, the early warning index system of coal mine safety production was given from four aspects as per- sonnel, environment, equipment and management. Then, improvement measures which are additional momentum method, adaptive learning rate, particle swarm optimization algorithm, variable weight method and asynchronous learning factor, are used to optimize BP neural network models. Further, the models are applied to a comparative study on coal mine safety warning instance. Results show that the identification precision of MPSO-BP network model is higher than GBP and PSO-BP model, and MPSO- BP model can not only effectively reduce the possibility of the network falling into a local minimum point, but also has fast convergence and high precision, which will provide the scientific basis for the forewarnin~ management of coal mine safetv production.

采用两步炭化法和熔盐模板法制备N、S共掺杂煤基硬炭及共储钠性能

硬炭因资源丰富、结构稳定及安全性高等优势,已成为钠离子电池常用阳极材料。其中,煤基衍生硬炭受到了广泛的关注。本工作以长焰煤为碳源,硫脲为氮硫源,NaCl为模板,通过两步炭化工艺和杂原子掺杂相结合的方法合成了N和S共掺杂的煤基硬炭(NSPC1200)。两步炭化过程在调节碳微晶结构和扩大层间距方面发挥了重要的作用。N和S的共掺杂调节了炭材料的电子结构,赋予其更多的活性位点;此外,引入NaCl作为模板有助于孔结构的构建,有利于电极和电解质之间的接触,从而实现Na+和电子的有效传输。在协同作用下,样品NSPC1200表现出优异的储钠能力,在20 mA g^(−1)电流密度下呈现314.2 mAh g^(−1)的可逆容量。即使在100 mA g^(−1)下循环200次,仍保持224.4 mAh g^(−1)的比容量。这项工作成功实现了策略性调整煤基炭材料微观结构的目标,最终获得了具有优异的电化学性能的硬炭阳极。